{"id":"https://openalex.org/W2145351510","doi":"https://doi.org/10.1145/1244408.1244416","title":"Extracting link spam using biased random walks from spam seed sets","display_name":"Extracting link spam using biased random walks from spam seed sets","publication_year":2007,"publication_date":"2007-05-08","ids":{"openalex":"https://openalex.org/W2145351510","doi":"https://doi.org/10.1145/1244408.1244416","mag":"2145351510"},"language":"en","primary_location":{"id":"doi:10.1145/1244408.1244416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034836937","display_name":"Baoning Wu","orcid":"https://orcid.org/0000-0002-9609-4325"},"institutions":[{"id":"https://openalex.org/I186143895","display_name":"Lehigh University","ror":"https://ror.org/012afjb06","country_code":"US","type":"education","lineage":["https://openalex.org/I186143895"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baoning Wu","raw_affiliation_strings":["Lehigh University, Bethlehem, PA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lehigh University, Bethlehem, PA","institution_ids":["https://openalex.org/I186143895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010424987","display_name":"Kumar Chellapilla","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kumar Chellapilla","raw_affiliation_strings":["Microsoft Live Labs, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Live Labs, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8359,"has_fulltext":false,"cited_by_count":34,"citation_normalized_percentile":{"value":0.92015209,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"44"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.754208505153656},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7341020107269287},{"id":"https://openalex.org/keywords/pagerank","display_name":"PageRank","score":0.702301561832428},{"id":"https://openalex.org/keywords/random-walk","display_name":"Random walk","score":0.6659159064292908},{"id":"https://openalex.org/keywords/link","display_name":"Link (geometry)","score":0.6410107612609863},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5135517120361328},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5099772214889526},{"id":"https://openalex.org/keywords/hyperlink","display_name":"Hyperlink","score":0.49706795811653137},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.49689438939094543},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.46621614694595337},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46162939071655273},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4422779679298401},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.4255621135234833},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.39479076862335205},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.328651487827301},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.2761760950088501},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.21581682562828064},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.21139854192733765},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19893565773963928},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.187605619430542},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.10537683963775635}],"concepts":[{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.754208505153656},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7341020107269287},{"id":"https://openalex.org/C2779172887","wikidata":"https://www.wikidata.org/wiki/Q184316","display_name":"PageRank","level":2,"score":0.702301561832428},{"id":"https://openalex.org/C121194460","wikidata":"https://www.wikidata.org/wiki/Q856741","display_name":"Random walk","level":2,"score":0.6659159064292908},{"id":"https://openalex.org/C2778753846","wikidata":"https://www.wikidata.org/wiki/Q6554239","display_name":"Link (geometry)","level":2,"score":0.6410107612609863},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5135517120361328},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5099772214889526},{"id":"https://openalex.org/C30088001","wikidata":"https://www.wikidata.org/wiki/Q102014","display_name":"Hyperlink","level":3,"score":0.49706795811653137},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.49689438939094543},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.46621614694595337},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46162939071655273},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4422779679298401},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.4255621135234833},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.39479076862335205},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.328651487827301},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.2761760950088501},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.21581682562828064},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.21139854192733765},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19893565773963928},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.187605619430542},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.10537683963775635},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1244408.1244416","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1244408.1244416","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 3rd international workshop on Adversarial information retrieval on the web","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.92.9394","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.92.9394","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://airweb.cse.lehigh.edu/2007/papers/paper_116.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W49362422","https://openalex.org/W202878612","https://openalex.org/W1660390307","https://openalex.org/W1764421085","https://openalex.org/W1845137714","https://openalex.org/W1951538275","https://openalex.org/W1984374364","https://openalex.org/W1987365175","https://openalex.org/W2043313142","https://openalex.org/W2045107949","https://openalex.org/W2050028965","https://openalex.org/W2066636486","https://openalex.org/W2076008912","https://openalex.org/W2084309732","https://openalex.org/W2108671511","https://openalex.org/W2118942057","https://openalex.org/W2122505515","https://openalex.org/W2138621811","https://openalex.org/W2139148100","https://openalex.org/W2151626491","https://openalex.org/W2156632103","https://openalex.org/W2169263924","https://openalex.org/W2169270715","https://openalex.org/W2293888960","https://openalex.org/W4249653116","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2245616560","https://openalex.org/W2351647974","https://openalex.org/W2116757369","https://openalex.org/W2583864867","https://openalex.org/W1558012608","https://openalex.org/W2139195016","https://openalex.org/W2096221717","https://openalex.org/W4248250357","https://openalex.org/W2542162642","https://openalex.org/W2150410176"],"abstract_inverted_index":{"Link":[0,23,40],"spam":[1,51,54,74,111,181],"deliberately":[2],"manipulates":[3],"hyperlinks":[4],"between":[5],"web":[6,61,125],"pages":[7],"in":[8,59,164,200,208],"order":[9,166],"to":[10,37,71,87,92,101,132,150,173],"unduly":[11],"boost":[12],"the":[13,60,83,116,124,134,138,142,153,160,174,194],"search":[14],"engine":[15],"ranking":[16,25],"of":[17,49,82,144,167],"one":[18,78],"or":[19,79],"more":[20,80],"target":[21],"pages.":[22],"based":[24],"algorithms":[26],"such":[27],"as":[28],"PageRank,":[29],"HITS,":[30],"and":[31,42,118,171,184,205],"other":[32],"derivatives":[33],"are":[34,45,162],"especially":[35],"vulnerable":[36],"link":[38,43,50,73,94,180,203,210],"spam.":[39],"farms":[41,204],"exchanges":[44],"two":[46],"common":[47],"instances":[48],"that":[52,193],"produce":[53],"communities":[55,75],"--":[56],"i.e.,":[57],"clusters":[58],"graph.":[62,126],"In":[63,85],"this":[64],"paper,":[65],"we":[66],"present":[67],"a":[68,109,120,188],"directed":[69],"approach":[70,106,195],"extracting":[72,201,209],"when":[76],"given":[77],"members":[81],"community.":[84],"contrast":[86],"previous":[88],"completely":[89],"automated":[90],"approaches":[91],"finding":[93],"spam,":[95],"our":[96],"method":[97],"is":[98,130,148],"specifically":[99],"designed":[100],"be":[102],"used":[103,149],"interactively.":[104],"Our":[105],"starts":[107],"with":[108],"small":[110],"seed":[112,139,190],"set":[113,140],"provided":[114],"by":[115],"user":[117],"simulates":[119],"random":[121,128,185],"walk":[122,129],"on":[123],"The":[127],"biased":[131],"explore":[133],"local":[135],"neighborhood":[136],"around":[137],"through":[141],"use":[143],"decay":[145],"probabilities.":[146],"Truncation":[147],"retain":[151],"only":[152],"most":[154],"frequently":[155],"visited":[156],"nodes.":[157],"After":[158],"termination,":[159],"nodes":[161],"sorted":[163],"decreasing":[165],"their":[168],"final":[169],"probabilities":[170],"presented":[172],"user.":[175],"Experiments":[176],"using":[177],"manually":[178],"labeled":[179],"data":[182],"sets":[183],"walks":[186],"from":[187],"single":[189],"domain":[191],"show":[192],"achieves":[196],"over":[197],"95.12%":[198],"precision":[199,207],"large":[202],"80.46%":[206],"exchange":[211],"centroids.":[212]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}